How much do you still code yourself?

Maybe a good analogy is playing music by ear versus relying on guitar chords you find online. The latter is convenient, but important details can easily slip through, even though those chords were originally written by humans. AI isn’t entirely different in that sense; it also builds on human-written material.

Learning a song by ear forces you to engage with it more deeply, and you’re more likely to remember it later. And, if you stop playing a song, eventually you forget how to play it.

deliberately avoiding AI just to keep those skills feels a bit like ignoring a very useful tool.

The very useful tool will shape the end results.

I avoid all AI tools in 2~3 personal projects that I feel strongly connected with.

I avoid all AI tools in 2~3 personal projects that I feel strongly connected with.ho

How is that making you feel?

In past years, I still had large PRs eventually hitting 2k LOC but I felt more connected with the code and people could asked me anything about it that I’d explain right away.

The very useful tool will shape the end results.

Could you elaborate on this?

Actually, the article explain well your point.

I always do a CR after the assistant and that makes me write ±500 LoCs daily myself.

Interesting. So you address feeedback yourself in order to write some code.

In order to deliver nifty elixir code instead of a spaghetty.

At work, we created some custom Credo rules for things we’ve kept seeing regardless of md files telling AI otherwise

My code is still 100% organic.

I’m underemployed so I can’t afford to have my code be generated by something.

Tell me about Credo rules

Still, no one Credo rule would catch case/2 where with/1 fits better, or is_binary(s) and s != "" instead of <<_::utf8, _::binary>> = s and much more. I am still able to figure out the elegant way of writing the code that no one existing model can.